© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 13739
    Prev
    Next
    INDEX
    Explanations

    words related to public events, politics, and well-known figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    352
    +0.11
    0.5%
    756
    +0.10
    0.5%
    669
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    747
    +0.11
    0.02
    72
    +0.10
    0.01
    737
    +0.10
    0.01
    Negative Logits
    pora
    -0.72
    knife
    -0.69
    scl
    -0.63
    execute
    -0.62
    Jump
    -0.61
    devices
    -0.61
    venants
    -0.60
    thur
    -0.58
    TN
    -0.58
    ubi
    -0.58
    POSITIVE LOGITS
    nered
    0.94
    dden
    0.90
    structed
    0.87
    itud
    0.80
    rand
    0.72
    ured
    0.69
    ceived
    0.69
    ersed
    0.68
    ubric
    0.66
    pared
    0.63
    Activations Density 0.061%

    No Known Activations